# MMSpec: Benchmarking Speculative Decoding for Vision-Language Models

arXiv: https://arxiv.org/abs/2603.14989 · HTML: https://mlsanity.com/paper/2603.14989/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Visual token pruning and efficiency, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 17 of its 21 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Visual token pruning and efficiency](https://mlsanity.com/mllm/visual-token-pruning-and-efficiency/)
- Efficient LLM inference and serving / [Fast autoregressive visual generation](https://mlsanity.com/inference/fast-autoregressive-visual-generation/)

## Builds on (most cited first, 17 of 17)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty](https://mlsanity.com/paper/2401.15077/) (2024)
- [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://mlsanity.com/paper/2409.02813/) (2024)
- [EAGLE-2: Faster Inference of Language Models with Dynamic Draft Trees](https://mlsanity.com/paper/2406.16858/) (2024)
- [EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test](https://mlsanity.com/paper/2503.01840/) (2025)
- [Break the Sequential Dependency of LLM Inference Using Lookahead Decoding](https://mlsanity.com/paper/2402.02057/) (2024)
- [Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding](https://mlsanity.com/paper/2401.07851/) (2024)
- [CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs](https://mlsanity.com/paper/2406.18521/) (2024)
- [Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token Recycling](https://mlsanity.com/paper/2408.08696/) (2024)
- [SAM Decoding: Speculative Decoding via Suffix Automaton](https://mlsanity.com/paper/2411.10666/) (2024)
- [Lookahead: An Inference Acceleration Framework for Large Language Model with Lossless Generation Accuracy](https://mlsanity.com/paper/2312.12728/) (2023)
- [ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Capability for Large Vision-Language Models](https://mlsanity.com/paper/2403.20194/) (2024)
- [ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding](https://mlsanity.com/paper/2509.15235/) (2025)
- [Speculative Decoding Reimagined for Multimodal Large Language Models](https://mlsanity.com/paper/2505.14260/) (2025)

## Built on by (most cited first, 3 of 3)

- [SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning](https://mlsanity.com/paper/2603.23483/) (2026)
- [Is Multimodal Speculative Decoding Ready for Diffusion-Based Parallel Drafting? A Survey and Empirical Diagnosis](https://mlsanity.com/paper/2608.20743/) (2026)
- [FOVEA: Focused On-Demand Visual Evidence Adaptation for Cache-Friendly Multimodal Speculative Decoding](https://mlsanity.com/paper/2608.22883/) (2026)

## Abstract (arXiv)

Vision-language models (VLMs) achieve strong performance on multimodal tasks but suffer from high inference latency due to large model sizes and long multimodal contexts. Speculative decoding has recently emerged as an effective acceleration technique, yet its behavior in VLMs remains insufficiently understood. We introduce MMSpec, the first benchmark for evaluating speculative decoding in vision-language models. MMSpec contains 600 multimodal samples across six task categories and integrates ten representative speculative decoding algorithms under a unified evaluation framework. Our study reveals three key findings: (1) methods designed for text-only LLMs degrade in multimodal scenarios, (2) vision awareness becomes increasingly important at larger batch sizes, and (3) throughput speedup alone does not reliably reflect latency performance. Motivated by these findings, we propose ViSkip, a plug-and-play speculative decoding method that dynamically adapts speculation to vision tokens and achieves state-of-the-art performance.